Combining Neural Network Forecasts on Wavelet-transformed Time Series

Alex Aussem, Fionn Murtagh

Research output: Contribution to journalArticlepeer-review

81 Citations (Scopus)


We discuss a simple strategy aimed at improving neural network prediction accuracy, based on the combination of predictions at varying resolution levels of the domain under investigation (here: time series). First, a wavelet transform is used to decompose the time series into varying scales of temporal resolution. The latter provides a sensible decomposition of the data so that the underlying temporal structures of the original time series become more tractable. Then, a dynamical recurrent neural netork is trained on each resolution scale with the temporal-recurrent backpropagation algorithm. By virtue of its internal dynamic, this general class of dynamic connections network approximates the underlying law governing each resolution level by a system of non-linear difference equations. The individual wavelet scale forecasts are afterwards recombined to form the current estimate. The predictive ability of this strategy is assessed with the sunspot series.

Original languageEnglish
Pages (from-to)113-122
Number of pages10
JournalConnection Science
Issue number1
Publication statusPublished - Mar 1997
Externally publishedYes


Dive into the research topics of 'Combining Neural Network Forecasts on Wavelet-transformed Time Series'. Together they form a unique fingerprint.

Cite this